Abstract
In this paper, we propose an adaptive audio watermarking scheme based on kernel fuzzy c-means (KFCM) clustering algorithm, which possesses robust ability against common signal processing and desynchronization attacks. The original audio signal is partitioned into audio frames and then each audio frame is further divided as two sub-frames. In order to resist desynchronization attacks, we embed a synchronization code into first sub-frame of each audio frame by using a mean quantization technique in temporal domain. Moreover, watermark signal is hid into DWT coefficients of second sub-frame of each audio frame by using an energy quantization technique. A local audio feature data set extracted from all audio frames is used to train a KFCM. The well-trained KFCM is used to adaptively control quantization steps in above two quantization techniques. The experimental results show the proposed scheme is robust to common signal processing (such as MP3 lossy compression, noise addition, filtering, re-sampling, re-quantizing) and desynchronization attacks (random cropping, pitch shifting, amplitude variation, time-scale modification, jittering).
Similar content being viewed by others
References
Chen LH, Lin JJ (2003) Mean quantization based image watermarking. Image Vis Comput 21:717–727
Cox IJ, Miller ML, Bloom JA (2002) Digital watermarking. Academic, London
Cox IJ, Miller ML, Bloom JA (2002) The first 50 year of electronic watermarking. J Appl Signal Process 2:126–132
Grin L, Marchand S (2004) Watermaking of speech signals using the sinusoidal model and frequency modulation of the partials. In: IEEE international conference on acoustics, and signal processing (ICASSP 2004), pp 633–636
Huang CH, Wu JL (2000) A watermark optimization technique based on genetic algorithms. In: The SPIE Electronic Imaging, 2000, San Jose, CA, pp 516–523
Huang CH, Wu JL (2009) Fidelity-guaranteed robustness enhancement of blind-detection watermarking schemes. Inf Sci 179:791–808
Ketcham M, Vongpraphip S (2007) Genetic algorithm audio watermarking using multiple image-based watermarks. In: International symposium on communications and information technologies, ISCIT’07, pp 1235–1240
Khan A (2006) A novel approach to decoding: exploiting anticipated attack information using genetic programming. Int J Knowl Based Intell Eng Syst 10(5):337–347
Khan A, Mirza AM (2007) Genetic perceptual shaping: utilizing cover image and conceivable attack information during watermark embedding. J Inf Fusion 8(4):354–365
Khan A, Tahir SF, Majid A, Choi TS (2008) Machine learning based adaptive watermark decoding in view of anticipated attack. Pattern Recogn 41:2594–2610
Kima DW, Leeb KY, Leea D, Leea KH (2005) Evaluation of the performance of clustering algorithms in kernel-induced feature space. Pattern Recogn 38:607–611
Kirbiz S, Gunsel B (2006) Robust audio watermark decoding by supervised learning. In: Proceedings of ICASSP 2006, vol 5, pp V-761–764
Kumsawat P, Attakitmongcol K, Srikaew A (2005) A new approach for optimization in image watermarking by using genetic algorithm. IEEE Trans Signal Process 53(12):4707–4719
Lee HS, Lee WS (2005) Audio watermarking through modification of tonal maskers. ETRI J 27(5):608–661
Li W, Xue XY (2003) An audio watermarking technique that is robust against ramdom cropping. Comput Music J 27(4):58–68
Liu JW, Xu MZ (2008) Kernelized fuzzy attribute c-means clustering algorithm. Fuzzy Sets Syst 159:2428–2445
Meng FM, Peng H, Pei Z, Wang J (2009) An adaptive image watermarking scheme based on support vector machine and genetic algorithm. Pattern Recogn Artif Intell 22(2):312–317 (in Chinese)
Peng H, Wang J, Zhang Z, Chen H, Zhang X (2010) Energy quantization modulation approach for image watermarking. J Comput Inf Syst 6(8):2675–2682
Peng H, Wang X, Wang W, Wang J, Hu DY (2010) Audio watermarking approach based on audio features in multiwavelet domain. J Comput Res Dev 47(2):216–222 (in Chinese)
Shawe-Taylor J, Cristianini N (2004) Kernel methods for pattern analysis. Cambridge University Press, Cambridge, England
Shieh CS, Huang HC, Wang FH, Pan JS (2004) Genetic watermarking based on transform domain techniques. Pattern Recogn 37(3):555–565
Vapnik V (2001) The nature of statistical learning theory. Springer, New York
Wang J, Lin FZ (2005) Digital audio watermarking based on support vector machine. J Comput Res Dev 42(9):1605–1611 (in Chinese)
Wu SQ, Huang JW, Shi YQ (2005) Efficiently self-synchronized audio watermarking for assured audio data transmission. IEEE Trans Broadcast 51(1):69–76
Xu XJ, Peng H, He CY (2007) DWT-based audio watermarking using support vector regression and subsampling. In: Masulli F, Mitra S, Pasi G (eds) Proceedings of WILF2007. LNAI, vol 4578, pp 136–144
Yang HJ, Patra JC, Chan CW (2002) An artificial neural network-based scheme for robust watermarking of audio signals. In: Proceeding of ICASSP’02, vol 1, pp I-1029–1032
Yusuf Y, Bilge G (2008) An integrated on-line audio watermark decoding scheme for broadcast monitoring. Multimed Tools Appl 40(1):1–21
Acknowledgements
This work was partially supported by Research Fund of Sichuan Provincial Key Discipline of Power Electronics and Electric Drive, Xihua University (No. SZD0503-09-0), Foundation of Sichuan Provincial Key Discipline of Computer Software and Theory (No. SZD0802-09-1), and Research Fund of Sichuan Key Laboratory of Intelligent Network Information Processing (SGXZD1002-10), China.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Peng, H., Wang, J. & Zhang, Z. Audio watermarking scheme robust against desynchronization attacks based on kernel clustering. Multimed Tools Appl 62, 681–699 (2013). https://doi.org/10.1007/s11042-011-0868-0
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-011-0868-0